Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3351 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.8651. Min Act: -0.1700
Data Index: 6076938 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.8339. Min Act: -0.1700
Data Index: 1000028 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.8026. Min Act: -0.1700
Data Index: 6765889 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.8339. Min Act: -0.1700
Data Index: 2008509 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.8026. Min Act: -0.1700
Data Index: 1139262 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.7401. Min Act: -0.1700
Data Index: 398837 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.7401. Min Act: -0.1700
Data Index: 6048476 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.7089. Min Act: -0.1700
Data Index: 6902815 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.7089. Min Act: -0.1700
Data Index: 2830228 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.7089. Min Act: -0.1700
Data Index: 1020110 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.6776. Min Act: -0.1700
Data Index: 1000027 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.6776. Min Act: -0.1700
Data Index: 6902817 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.6776. Min Act: -0.1700
Data Index: 1798907 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.6776. Min Act: -0.1700
Data Index: 6398662 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.6464. Min Act: -0.1700
Data Index: 4397429 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.6464. Min Act: -0.1700
Data Index: 6703204 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.6151. Min Act: -0.1700
Data Index: 1076456 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.6464. Min Act: -0.1700
Data Index: 7358664 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.6464. Min Act: -0.1700
Data Index: 2773577 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.6464. Min Act: -0.1700
Data Index: 490877 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #19